1. Create a simple 15-node, one hidden layer

regression MLP using the command 'fitnet. Use the

network with its default settings except for

training/validation/test data partitioning ratios,

which you shall set to 70%, 15%, and 15%

respectively. Find the mean and variance of MSEs

for training, validation, and testing portions of the

dataset from the 10 training repetitions (with

random initializations using init(net)).

2. Change the network's hidden layer size to 2 nodes

and then to 80 nodes, with training, validation, and

testing ratios set to 30%, 20%, and 50%; and then

find the mean and variance of MSEs for training.

validation, and test portions of the dataset from the

10 training repetitions (again with random model

initializations).

3. For the 80-node model, have regularization (weight

decay) set at 0.1 and 0.5 and the find mean and

variance of MSEs for training and validation

portions of the dataset from the 10 repetitions for

each case.